[patch -mm 22/28] x86_64: Convert to cleckevents

From: Thomas Gleixner
Date: Sat Jun 23 2007 - 09:30:00 EST

Convert x86_64 to the clockevents code. Share code with i386 for
hpet and PIT.

Build and whitespace fixups from:
Venki Pallipadi <venkatesh.pallipadi@xxxxxxxxx>
and
Chris Wright <chrisw@xxxxxxxxxxxx>

Based on an initial patch from Chris Wright <chrisw@xxxxxxxxxxxx>

Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Chris Wright <chrisw@xxxxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxx>

---
arch/i386/kernel/hpet.c | 50 +++
arch/i386/kernel/i8253.c | 3
arch/x86_64/Kconfig | 12
arch/x86_64/kernel/Makefile | 4
arch/x86_64/kernel/apic.c | 563 ++++++++++++++++++++++++-------------------
arch/x86_64/kernel/hpet.c | 493 -------------------------------------
arch/x86_64/kernel/i8259.c | 47 ---
arch/x86_64/kernel/smpboot.c | 4
arch/x86_64/kernel/time.c | 253 ++-----------------
arch/x86_64/kernel/tsc.c | 90 ++++++
include/asm-i386/hpet.h | 125 +++------
include/asm-i386/tsc.h | 4
include/asm-x86_64/apic.h | 6
include/asm-x86_64/hpet.h | 77 -----
include/asm-x86_64/i8253.h | 8
include/asm-x86_64/proto.h | 3
16 files changed, 557 insertions(+), 1185 deletions(-)

Index: linux-2.6.22-rc4-mm/arch/x86_64/kernel/time.c
===================================================================
--- linux-2.6.22-rc4-mm.orig/arch/x86_64/kernel/time.c 2007-06-23 14:38:59.000000000 +0200
+++ linux-2.6.22-rc4-mm/arch/x86_64/kernel/time.c 2007-06-23 14:39:00.000000000 +0200
@@ -28,11 +28,11 @@
#include <linux/cpu.h>
#include <linux/kallsyms.h>
#include <linux/acpi.h>
+#include <linux/clockchips.h>
#ifdef CONFIG_ACPI
#include <acpi/achware.h> /* for PM timer frequency */
#include <acpi/acpi_bus.h>
#endif
-#include <asm/8253pit.h>
#include <asm/i8253.h>
#include <asm/pgtable.h>
#include <asm/vsyscall.h>
@@ -47,12 +47,8 @@
#include <asm/nmi.h>
#include <asm/vgtod.h>

-static char *timename = NULL;
-
DEFINE_SPINLOCK(rtc_lock);
EXPORT_SYMBOL(rtc_lock);
-DEFINE_SPINLOCK(i8253_lock);
-EXPORT_SYMBOL(i8253_lock);

volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;

@@ -153,49 +149,14 @@ int update_persistent_clock(struct times
return set_rtc_mmss(now.tv_sec);
}

-void main_timer_handler(void)
-{
-/*
- * Here we are in the timer irq handler. We have irqs locally disabled (so we
- * don't need spin_lock_irqsave()) but we don't know if the timer_bh is running
- * on the other CPU, so we need a lock. We also need to lock the vsyscall
- * variables, because both do_timer() and us change them -arca+vojtech
- */
-
- write_seqlock(&xtime_lock);
-
-/*
- * Do the timer stuff.
- */
-
- do_timer(1);
-#ifndef CONFIG_SMP
- update_process_times(user_mode(get_irq_regs()));
-#endif
-
-/*
- * In the SMP case we use the local APIC timer interrupt to do the profiling,
- * except when we simulate SMP mode on a uniprocessor system, in that case we
- * have to call the local interrupt handler.
- */
-
- if (!using_apic_timer)
- smp_local_timer_interrupt();
-
- write_sequnlock(&xtime_lock);
-}
-
static irqreturn_t timer_interrupt(int irq, void *dev_id)
{
- if (apic_runs_main_timer > 1)
- return IRQ_HANDLED;
- main_timer_handler();
- if (using_apic_timer)
- smp_send_timer_broadcast_ipi();
+ global_clock_event->event_handler(global_clock_event);
+
return IRQ_HANDLED;
}

-static unsigned long get_cmos_time(void)
+unsigned long read_persistent_clock(void)
{
unsigned int year, mon, day, hour, min, sec;
unsigned long flags;
@@ -222,7 +183,7 @@ static unsigned long get_cmos_time(void)
/*
* We know that x86-64 always uses BCD format, no need to check the
* config register.
- */
+ */

BCD_TO_BIN(sec);
BCD_TO_BIN(min);
@@ -235,11 +196,11 @@ static unsigned long get_cmos_time(void)
BCD_TO_BIN(century);
year += century * 100;
printk(KERN_INFO "Extended CMOS year: %d\n", century * 100);
- } else {
+ } else {
/*
* x86-64 systems only exists since 2002.
* This will work up to Dec 31, 2100
- */
+ */
year += 2000;
}

@@ -257,17 +218,17 @@ static unsigned int __init tsc_calibrate
unsigned long flags;

for (i = 0; i < 4; i++)
- if (avail_to_resrv_perfctr_nmi_bit(i))
- break;
+ if (avail_to_resrv_perfctr_nmi_bit(i))
+ break;
no_ctr_free = (i == 4);
if (no_ctr_free) {
- i = 3;
- rdmsrl(MSR_K7_EVNTSEL3, evntsel3);
- wrmsrl(MSR_K7_EVNTSEL3, 0);
- rdmsrl(MSR_K7_PERFCTR3, pmc3);
+ i = 3;
+ rdmsrl(MSR_K7_EVNTSEL3, evntsel3);
+ wrmsrl(MSR_K7_EVNTSEL3, 0);
+ rdmsrl(MSR_K7_PERFCTR3, pmc3);
} else {
- reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i);
- reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
+ reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i);
+ reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
}
local_irq_save(flags);
/* start meauring cycles, incrementing from 0 */
@@ -275,119 +236,38 @@ static unsigned int __init tsc_calibrate
wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76);
rdtscl(tsc_start);
do {
- rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now);
- tsc_now = get_cycles_sync();
+ rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now);
+ tsc_now = get_cycles_sync();
} while ((tsc_now - tsc_start) < TICK_COUNT);

local_irq_restore(flags);
if (no_ctr_free) {
- wrmsrl(MSR_K7_EVNTSEL3, 0);
- wrmsrl(MSR_K7_PERFCTR3, pmc3);
- wrmsrl(MSR_K7_EVNTSEL3, evntsel3);
+ wrmsrl(MSR_K7_EVNTSEL3, 0);
+ wrmsrl(MSR_K7_PERFCTR3, pmc3);
+ wrmsrl(MSR_K7_EVNTSEL3, evntsel3);
} else {
- release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
- release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
+ release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
+ release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
}

return pmc_now * tsc_khz / (tsc_now - tsc_start);
}

-/*
- * pit_calibrate_tsc() uses the speaker output (channel 2) of
- * the PIT. This is better than using the timer interrupt output,
- * because we can read the value of the speaker with just one inb(),
- * where we need three i/o operations for the interrupt channel.
- * We count how many ticks the TSC does in 50 ms.
- */
-
-static unsigned int __init pit_calibrate_tsc(void)
-{
- unsigned long start, end;
- unsigned long flags;
-
- spin_lock_irqsave(&i8253_lock, flags);
-
- outb((inb(0x61) & ~0x02) | 0x01, 0x61);
-
- outb(0xb0, 0x43);
- outb((PIT_TICK_RATE / (1000 / 50)) & 0xff, 0x42);
- outb((PIT_TICK_RATE / (1000 / 50)) >> 8, 0x42);
- start = get_cycles_sync();
- while ((inb(0x61) & 0x20) == 0);
- end = get_cycles_sync();
-
- spin_unlock_irqrestore(&i8253_lock, flags);
-
- return (end - start) / 50;
-}
-
-#define PIT_MODE 0x43
-#define PIT_CH0 0x40
-
-static void __pit_init(int val, u8 mode)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&i8253_lock, flags);
- outb_p(mode, PIT_MODE);
- outb_p(val & 0xff, PIT_CH0); /* LSB */
- outb_p(val >> 8, PIT_CH0); /* MSB */
- spin_unlock_irqrestore(&i8253_lock, flags);
-}
-
-void __init pit_init(void)
-{
- __pit_init(LATCH, 0x34); /* binary, mode 2, LSB/MSB, ch 0 */
-}
-
-void pit_stop_interrupt(void)
-{
- __pit_init(0, 0x30); /* mode 0 */
-}
-
-void stop_timer_interrupt(void)
-{
- char *name;
- if (hpet_address) {
- name = "HPET";
- hpet_timer_stop_set_go(0);
- } else {
- name = "PIT";
- pit_stop_interrupt();
- }
- printk(KERN_INFO "timer: %s interrupt stopped.\n", name);
-}
-
static struct irqaction irq0 = {
.handler = timer_interrupt,
.flags = IRQF_DISABLED | IRQF_IRQPOLL,
.mask = CPU_MASK_NONE,
- .name = "timer"
+ .name = "timer"
};

void __init time_init(void)
{
- if (nohpet)
- hpet_address = 0;
- xtime.tv_sec = get_cmos_time();
- xtime.tv_nsec = 0;
-
- set_normalized_timespec(&wall_to_monotonic,
- -xtime.tv_sec, -xtime.tv_nsec);
-
- if (hpet_arch_init())
- hpet_address = 0;
-
- if (hpet_use_timer) {
- /* set tick_nsec to use the proper rate for HPET */
- tick_nsec = TICK_NSEC_HPET;
- tsc_khz = hpet_calibrate_tsc();
- timename = "HPET";
- } else {
- pit_init();
- tsc_khz = pit_calibrate_tsc();
- timename = "PIT";
- }
+ if (!hpet_enable())
+ setup_pit_timer();
+
+ setup_irq(0, &irq0);
+
+ tsc_calibrate();

cpu_khz = tsc_khz;
if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) &&
@@ -406,79 +286,4 @@ void __init time_init(void)
printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n",
cpu_khz / 1000, cpu_khz % 1000);
init_tsc_clocksource();
-
- setup_irq(0, &irq0);
}
-
-
-static long clock_cmos_diff;
-static unsigned long sleep_start;
-
-/*
- * sysfs support for the timer.
- */
-
-static int timer_suspend(struct sys_device *dev, pm_message_t state)
-{
- /*
- * Estimate time zone so that set_time can update the clock
- */
- long cmos_time = get_cmos_time();
-
- clock_cmos_diff = -cmos_time;
- clock_cmos_diff += get_seconds();
- sleep_start = cmos_time;
- return 0;
-}
-
-static int timer_resume(struct sys_device *dev)
-{
- unsigned long flags;
- unsigned long sec;
- unsigned long ctime = get_cmos_time();
- long sleep_length = (ctime - sleep_start) * HZ;
-
- if (sleep_length < 0) {
- printk(KERN_WARNING "Time skew detected in timer resume!\n");
- /* The time after the resume must not be earlier than the time
- * before the suspend or some nasty things will happen
- */
- sleep_length = 0;
- ctime = sleep_start;
- }
- if (hpet_address)
- hpet_reenable();
- else
- i8254_timer_resume();
-
- sec = ctime + clock_cmos_diff;
- write_seqlock_irqsave(&xtime_lock,flags);
- xtime.tv_sec = sec;
- xtime.tv_nsec = 0;
- jiffies += sleep_length;
- write_sequnlock_irqrestore(&xtime_lock,flags);
- touch_softlockup_watchdog();
- return 0;
-}
-
-static struct sysdev_class timer_sysclass = {
- .resume = timer_resume,
- .suspend = timer_suspend,
- set_kset_name("timer"),
-};
-
-/* XXX this sysfs stuff should probably go elsewhere later -john */
-static struct sys_device device_timer = {
- .id = 0,
- .cls = &timer_sysclass,
-};
-
-static int time_init_device(void)
-{
- int error = sysdev_class_register(&timer_sysclass);
- if (!error)
- error = sysdev_register(&device_timer);
- return error;
-}
-
-device_initcall(time_init_device);
Index: linux-2.6.22-rc4-mm/arch/x86_64/kernel/hpet.c
===================================================================
--- linux-2.6.22-rc4-mm.orig/arch/x86_64/kernel/hpet.c 2007-06-23 14:38:54.000000000 +0200
+++ /dev/null 1970-01-01 00:00:00.000000000 +0000
@@ -1,493 +0,0 @@
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/mc146818rtc.h>
-#include <linux/time.h>
-#include <linux/clocksource.h>
-#include <linux/ioport.h>
-#include <linux/acpi.h>
-#include <linux/hpet.h>
-#include <asm/pgtable.h>
-#include <asm/vsyscall.h>
-#include <asm/timex.h>
-#include <asm/hpet.h>
-
-#define HPET_MASK 0xFFFFFFFF
-#define HPET_SHIFT 22
-
-/* FSEC = 10^-15 NSEC = 10^-9 */
-#define FSEC_PER_NSEC 1000000
-
-int nohpet __initdata;
-
-unsigned long hpet_address;
-unsigned long hpet_period; /* fsecs / HPET clock */
-unsigned long hpet_tick; /* HPET clocks / interrupt */
-
-int hpet_use_timer; /* Use counter of hpet for time keeping,
- * otherwise PIT
- */
-
-#ifdef CONFIG_HPET
-static __init int late_hpet_init(void)
-{
- struct hpet_data hd;
- unsigned int ntimer;
-
- if (!hpet_address)
- return 0;
-
- memset(&hd, 0, sizeof(hd));
-
- ntimer = hpet_readl(HPET_ID);
- ntimer = (ntimer & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT;
- ntimer++;
-
- /*
- * Register with driver.
- * Timer0 and Timer1 is used by platform.
- */
- hd.hd_phys_address = hpet_address;
- hd.hd_address = (void __iomem *)fix_to_virt(FIX_HPET_BASE);
- hd.hd_nirqs = ntimer;
- hd.hd_flags = HPET_DATA_PLATFORM;
- hpet_reserve_timer(&hd, 0);
-#ifdef CONFIG_HPET_EMULATE_RTC
- hpet_reserve_timer(&hd, 1);
-#endif
- hd.hd_irq[0] = HPET_LEGACY_8254;
- hd.hd_irq[1] = HPET_LEGACY_RTC;
- if (ntimer > 2) {
- struct hpet *hpet;
- struct hpet_timer *timer;
- int i;
-
- hpet = (struct hpet *) fix_to_virt(FIX_HPET_BASE);
- timer = &hpet->hpet_timers[2];
- for (i = 2; i < ntimer; timer++, i++)
- hd.hd_irq[i] = (timer->hpet_config &
- Tn_INT_ROUTE_CNF_MASK) >>
- Tn_INT_ROUTE_CNF_SHIFT;
-
- }
-
- hpet_alloc(&hd);
- return 0;
-}
-fs_initcall(late_hpet_init);
-#endif
-
-int hpet_timer_stop_set_go(unsigned long tick)
-{
- unsigned int cfg;
-
-/*
- * Stop the timers and reset the main counter.
- */
-
- cfg = hpet_readl(HPET_CFG);
- cfg &= ~(HPET_CFG_ENABLE | HPET_CFG_LEGACY);
- hpet_writel(cfg, HPET_CFG);
- hpet_writel(0, HPET_COUNTER);
- hpet_writel(0, HPET_COUNTER + 4);
-
-/*
- * Set up timer 0, as periodic with first interrupt to happen at hpet_tick,
- * and period also hpet_tick.
- */
- if (hpet_use_timer) {
- hpet_writel(HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL |
- HPET_TN_32BIT, HPET_T0_CFG);
- hpet_writel(hpet_tick, HPET_T0_CMP); /* next interrupt */
- hpet_writel(hpet_tick, HPET_T0_CMP); /* period */
- cfg |= HPET_CFG_LEGACY;
- }
-/*
- * Go!
- */
-
- cfg |= HPET_CFG_ENABLE;
- hpet_writel(cfg, HPET_CFG);
-
- return 0;
-}
-
-static cycle_t read_hpet(void)
-{
- return (cycle_t)hpet_readl(HPET_COUNTER);
-}
-
-static cycle_t __vsyscall_fn vread_hpet(void)
-{
- return readl((void __iomem *)fix_to_virt(VSYSCALL_HPET) + 0xf0);
-}
-
-struct clocksource clocksource_hpet = {
- .name = "hpet",
- .rating = 250,
- .read = read_hpet,
- .mask = (cycle_t)HPET_MASK,
- .mult = 0, /* set below */
- .shift = HPET_SHIFT,
- .flags = CLOCK_SOURCE_IS_CONTINUOUS,
- .vread = vread_hpet,
-};
-
-int hpet_arch_init(void)
-{
- unsigned int id;
- u64 tmp;
-
- if (!hpet_address)
- return -1;
- set_fixmap_nocache(FIX_HPET_BASE, hpet_address);
- __set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE);
-
-/*
- * Read the period, compute tick and quotient.
- */
-
- id = hpet_readl(HPET_ID);
-
- if (!(id & HPET_ID_VENDOR) || !(id & HPET_ID_NUMBER))
- return -1;
-
- hpet_period = hpet_readl(HPET_PERIOD);
- if (hpet_period < 100000 || hpet_period > 100000000)
- return -1;
-
- hpet_tick = (FSEC_PER_TICK + hpet_period / 2) / hpet_period;
-
- hpet_use_timer = (id & HPET_ID_LEGSUP);
-
- /*
- * hpet period is in femto seconds per cycle
- * so we need to convert this to ns/cyc units
- * aproximated by mult/2^shift
- *
- * fsec/cyc * 1nsec/1000000fsec = nsec/cyc = mult/2^shift
- * fsec/cyc * 1ns/1000000fsec * 2^shift = mult
- * fsec/cyc * 2^shift * 1nsec/1000000fsec = mult
- * (fsec/cyc << shift)/1000000 = mult
- * (hpet_period << shift)/FSEC_PER_NSEC = mult
- */
- tmp = (u64)hpet_period << HPET_SHIFT;
- do_div(tmp, FSEC_PER_NSEC);
- clocksource_hpet.mult = (u32)tmp;
- clocksource_register(&clocksource_hpet);
-
- return hpet_timer_stop_set_go(hpet_tick);
-}
-
-int hpet_reenable(void)
-{
- return hpet_timer_stop_set_go(hpet_tick);
-}
-
-/*
- * calibrate_tsc() calibrates the processor TSC in a very simple way, comparing
- * it to the HPET timer of known frequency.
- */
-
-#define TICK_COUNT 100000000
-#define TICK_MIN 5000
-#define MAX_TRIES 5
-
-/*
- * Some platforms take periodic SMI interrupts with 5ms duration. Make sure none
- * occurs between the reads of the hpet & TSC.
- */
-static void __init read_hpet_tsc(int *hpet, int *tsc)
-{
- int tsc1, tsc2, hpet1, i;
-
- for (i = 0; i < MAX_TRIES; i++) {
- tsc1 = get_cycles_sync();
- hpet1 = hpet_readl(HPET_COUNTER);
- tsc2 = get_cycles_sync();
- if (tsc2 - tsc1 > TICK_MIN)
- break;
- }
- *hpet = hpet1;
- *tsc = tsc2;
-}
-
-unsigned int __init hpet_calibrate_tsc(void)
-{
- int tsc_start, hpet_start;
- int tsc_now, hpet_now;
- unsigned long flags;
-
- local_irq_save(flags);
-
- read_hpet_tsc(&hpet_start, &tsc_start);
-
- do {
- local_irq_disable();
- read_hpet_tsc(&hpet_now, &tsc_now);
- local_irq_restore(flags);
- } while ((tsc_now - tsc_start) < TICK_COUNT &&
- (hpet_now - hpet_start) < TICK_COUNT);
-
- return (tsc_now - tsc_start) * 1000000000L
- / ((hpet_now - hpet_start) * hpet_period / 1000);
-}
-
-#ifdef CONFIG_HPET_EMULATE_RTC
-/* HPET in LegacyReplacement Mode eats up RTC interrupt line. When, HPET
- * is enabled, we support RTC interrupt functionality in software.
- * RTC has 3 kinds of interrupts:
- * 1) Update Interrupt - generate an interrupt, every sec, when RTC clock
- * is updated
- * 2) Alarm Interrupt - generate an interrupt at a specific time of day
- * 3) Periodic Interrupt - generate periodic interrupt, with frequencies
- * 2Hz-8192Hz (2Hz-64Hz for non-root user) (all freqs in powers of 2)
- * (1) and (2) above are implemented using polling at a frequency of
- * 64 Hz. The exact frequency is a tradeoff between accuracy and interrupt
- * overhead. (DEFAULT_RTC_INT_FREQ)
- * For (3), we use interrupts at 64Hz or user specified periodic
- * frequency, whichever is higher.
- */
-#include <linux/rtc.h>
-
-#define DEFAULT_RTC_INT_FREQ 64
-#define RTC_NUM_INTS 1
-
-static unsigned long UIE_on;
-static unsigned long prev_update_sec;
-
-static unsigned long AIE_on;
-static struct rtc_time alarm_time;
-
-static unsigned long PIE_on;
-static unsigned long PIE_freq = DEFAULT_RTC_INT_FREQ;
-static unsigned long PIE_count;
-
-static unsigned long hpet_rtc_int_freq; /* RTC interrupt frequency */
-static unsigned int hpet_t1_cmp; /* cached comparator register */
-
-int is_hpet_enabled(void)
-{
- return hpet_address != 0;
-}
-
-/*
- * Timer 1 for RTC, we do not use periodic interrupt feature,
- * even if HPET supports periodic interrupts on Timer 1.
- * The reason being, to set up a periodic interrupt in HPET, we need to
- * stop the main counter. And if we do that everytime someone diables/enables
- * RTC, we will have adverse effect on main kernel timer running on Timer 0.
- * So, for the time being, simulate the periodic interrupt in software.
- *
- * hpet_rtc_timer_init() is called for the first time and during subsequent
- * interuppts reinit happens through hpet_rtc_timer_reinit().
- */
-int hpet_rtc_timer_init(void)
-{
- unsigned int cfg, cnt;
- unsigned long flags;
-
- if (!is_hpet_enabled())
- return 0;
- /*
- * Set the counter 1 and enable the interrupts.
- */
- if (PIE_on && (PIE_freq > DEFAULT_RTC_INT_FREQ))
- hpet_rtc_int_freq = PIE_freq;
- else
- hpet_rtc_int_freq = DEFAULT_RTC_INT_FREQ;
-
- local_irq_save(flags);
-
- cnt = hpet_readl(HPET_COUNTER);
- cnt += ((hpet_tick*HZ)/hpet_rtc_int_freq);
- hpet_writel(cnt, HPET_T1_CMP);
- hpet_t1_cmp = cnt;
-
- cfg = hpet_readl(HPET_T1_CFG);
- cfg &= ~HPET_TN_PERIODIC;
- cfg |= HPET_TN_ENABLE | HPET_TN_32BIT;
- hpet_writel(cfg, HPET_T1_CFG);
-
- local_irq_restore(flags);
-
- return 1;
-}
-
-static void hpet_rtc_timer_reinit(void)
-{
- unsigned int cfg, cnt, ticks_per_int, lost_ints;
-
- if (unlikely(!(PIE_on | AIE_on | UIE_on))) {
- cfg = hpet_readl(HPET_T1_CFG);
- cfg &= ~HPET_TN_ENABLE;
- hpet_writel(cfg, HPET_T1_CFG);
- return;
- }
-
- if (PIE_on && (PIE_freq > DEFAULT_RTC_INT_FREQ))
- hpet_rtc_int_freq = PIE_freq;
- else
- hpet_rtc_int_freq = DEFAULT_RTC_INT_FREQ;
-
- /* It is more accurate to use the comparator value than current count.*/
- ticks_per_int = hpet_tick * HZ / hpet_rtc_int_freq;
- hpet_t1_cmp += ticks_per_int;
- hpet_writel(hpet_t1_cmp, HPET_T1_CMP);
-
- /*
- * If the interrupt handler was delayed too long, the write above tries
- * to schedule the next interrupt in the past and the hardware would
- * not interrupt until the counter had wrapped around.
- * So we have to check that the comparator wasn't set to a past time.
- */
- cnt = hpet_readl(HPET_COUNTER);
- if (unlikely((int)(cnt - hpet_t1_cmp) > 0)) {
- lost_ints = (cnt - hpet_t1_cmp) / ticks_per_int + 1;
- /* Make sure that, even with the time needed to execute
- * this code, the next scheduled interrupt has been moved
- * back to the future: */
- lost_ints++;
-
- hpet_t1_cmp += lost_ints * ticks_per_int;
- hpet_writel(hpet_t1_cmp, HPET_T1_CMP);
-
- if (PIE_on)
- PIE_count += lost_ints;
-
- if (printk_ratelimit())
- printk(KERN_WARNING "rtc: lost some interrupts at %ldHz.\n",
- hpet_rtc_int_freq);
- }
-}
-
-/*
- * The functions below are called from rtc driver.
- * Return 0 if HPET is not being used.
- * Otherwise do the necessary changes and return 1.
- */
-int hpet_mask_rtc_irq_bit(unsigned long bit_mask)
-{
- if (!is_hpet_enabled())
- return 0;
-
- if (bit_mask & RTC_UIE)
- UIE_on = 0;
- if (bit_mask & RTC_PIE)
- PIE_on = 0;
- if (bit_mask & RTC_AIE)
- AIE_on = 0;
-
- return 1;
-}
-
-int hpet_set_rtc_irq_bit(unsigned long bit_mask)
-{
- int timer_init_reqd = 0;
-
- if (!is_hpet_enabled())
- return 0;
-
- if (!(PIE_on | AIE_on | UIE_on))
- timer_init_reqd = 1;
-
- if (bit_mask & RTC_UIE) {
- UIE_on = 1;
- }
- if (bit_mask & RTC_PIE) {
- PIE_on = 1;
- PIE_count = 0;
- }
- if (bit_mask & RTC_AIE) {
- AIE_on = 1;
- }
-
- if (timer_init_reqd)
- hpet_rtc_timer_init();
-
- return 1;
-}
-
-int hpet_set_alarm_time(unsigned char hrs, unsigned char min, unsigned char sec)
-{
- if (!is_hpet_enabled())
- return 0;
-
- alarm_time.tm_hour = hrs;
- alarm_time.tm_min = min;
- alarm_time.tm_sec = sec;
-
- return 1;
-}
-
-int hpet_set_periodic_freq(unsigned long freq)
-{
- if (!is_hpet_enabled())
- return 0;
-
- PIE_freq = freq;
- PIE_count = 0;
-
- return 1;
-}
-
-int hpet_rtc_dropped_irq(void)
-{
- if (!is_hpet_enabled())
- return 0;
-
- return 1;
-}
-
-irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id, struct pt_regs *regs)
-{
- struct rtc_time curr_time;
- unsigned long rtc_int_flag = 0;
- int call_rtc_interrupt = 0;
-
- hpet_rtc_timer_reinit();
-
- if (UIE_on | AIE_on) {
- rtc_get_rtc_time(&curr_time);
- }
- if (UIE_on) {
- if (curr_time.tm_sec != prev_update_sec) {
- /* Set update int info, call real rtc int routine */
- call_rtc_interrupt = 1;
- rtc_int_flag = RTC_UF;
- prev_update_sec = curr_time.tm_sec;
- }
- }
- if (PIE_on) {
- PIE_count++;
- if (PIE_count >= hpet_rtc_int_freq/PIE_freq) {
- /* Set periodic int info, call real rtc int routine */
- call_rtc_interrupt = 1;
- rtc_int_flag |= RTC_PF;
- PIE_count = 0;
- }
- }
- if (AIE_on) {
- if ((curr_time.tm_sec == alarm_time.tm_sec) &&
- (curr_time.tm_min == alarm_time.tm_min) &&
- (curr_time.tm_hour == alarm_time.tm_hour)) {
- /* Set alarm int info, call real rtc int routine */
- call_rtc_interrupt = 1;
- rtc_int_flag |= RTC_AF;
- }
- }
- if (call_rtc_interrupt) {
- rtc_int_flag |= (RTC_IRQF | (RTC_NUM_INTS << 8));
- rtc_interrupt(rtc_int_flag, dev_id);
- }
- return IRQ_HANDLED;
-}
-#endif
-
-static int __init nohpet_setup(char *s)
-{
- nohpet = 1;
- return 1;
-}
-
-__setup("nohpet", nohpet_setup);
Index: linux-2.6.22-rc4-mm/arch/x86_64/Kconfig
===================================================================
--- linux-2.6.22-rc4-mm.orig/arch/x86_64/Kconfig 2007-06-23 14:38:59.000000000 +0200
+++ linux-2.6.22-rc4-mm/arch/x86_64/Kconfig 2007-06-23 14:39:00.000000000 +0200
@@ -28,6 +28,18 @@ config GENERIC_TIME
bool
default y

+config GENERIC_CLOCKEVENTS
+ bool
+ default y
+
+config GENERIC_CLOCKEVENTS_BROADCAST
+ bool
+ default y
+
+config NONIRQ_WAKEUP
+ bool
+ default y
+
config GENERIC_TIME_VSYSCALL
bool
default y
Index: linux-2.6.22-rc4-mm/include/asm-x86_64/hpet.h
===================================================================
--- linux-2.6.22-rc4-mm.orig/include/asm-x86_64/hpet.h 2007-06-23 14:38:59.000000000 +0200
+++ linux-2.6.22-rc4-mm/include/asm-x86_64/hpet.h 2007-06-23 14:39:00.000000000 +0200
@@ -1,77 +1,2 @@
-#ifndef _ASM_X8664_HPET_H
-#define _ASM_X8664_HPET_H 1

-/*
- * Documentation on HPET can be found at:
- * http://www.intel.com/ial/home/sp/pcmmspec.htm
- * ftp://download.intel.com/ial/home/sp/mmts098.pdf
- */
-
-#define HPET_MMAP_SIZE 1024
-
-#define HPET_ID 0x000
-#define HPET_PERIOD 0x004
-#define HPET_CFG 0x010
-#define HPET_STATUS 0x020
-#define HPET_COUNTER 0x0f0
-#define HPET_Tn_OFFSET 0x20
-#define HPET_Tn_CFG(n) (0x100 + (n) * HPET_Tn_OFFSET)
-#define HPET_Tn_ROUTE(n) (0x104 + (n) * HPET_Tn_OFFSET)
-#define HPET_Tn_CMP(n) (0x108 + (n) * HPET_Tn_OFFSET)
-#define HPET_T0_CFG HPET_Tn_CFG(0)
-#define HPET_T0_CMP HPET_Tn_CMP(0)
-#define HPET_T1_CFG HPET_Tn_CFG(1)
-#define HPET_T1_CMP HPET_Tn_CMP(1)
-
-#define HPET_ID_VENDOR 0xffff0000
-#define HPET_ID_LEGSUP 0x00008000
-#define HPET_ID_64BIT 0x00002000
-#define HPET_ID_NUMBER 0x00001f00
-#define HPET_ID_REV 0x000000ff
-#define HPET_ID_NUMBER_SHIFT 8
-
-#define HPET_ID_VENDOR_SHIFT 16
-#define HPET_ID_VENDOR_8086 0x8086
-
-#define HPET_CFG_ENABLE 0x001
-#define HPET_CFG_LEGACY 0x002
-#define HPET_LEGACY_8254 2
-#define HPET_LEGACY_RTC 8
-
-#define HPET_TN_LEVEL 0x0002
-#define HPET_TN_ENABLE 0x0004
-#define HPET_TN_PERIODIC 0x0008
-#define HPET_TN_PERIODIC_CAP 0x0010
-#define HPET_TN_64BIT_CAP 0x0020
-#define HPET_TN_SETVAL 0x0040
-#define HPET_TN_32BIT 0x0100
-#define HPET_TN_ROUTE 0x3e00
-#define HPET_TN_FSB 0x4000
-#define HPET_TN_FSB_CAP 0x8000
-
-#define HPET_TN_ROUTE_SHIFT 9
-
-#define HPET_TICK_RATE (HZ * 100000UL)
-
-extern int is_hpet_enabled(void);
-extern int hpet_rtc_timer_init(void);
-extern int hpet_arch_init(void);
-extern int hpet_timer_stop_set_go(unsigned long tick);
-extern int hpet_reenable(void);
-extern unsigned int hpet_calibrate_tsc(void);
-
-extern int hpet_use_timer;
-extern unsigned long hpet_address;
-extern unsigned long hpet_period;
-extern unsigned long hpet_tick;
-
-#ifdef CONFIG_HPET_EMULATE_RTC
-extern int hpet_mask_rtc_irq_bit(unsigned long bit_mask);
-extern int hpet_set_rtc_irq_bit(unsigned long bit_mask);
-extern int hpet_set_alarm_time(unsigned char hrs, unsigned char min, unsigned char sec);
-extern int hpet_set_periodic_freq(unsigned long freq);
-extern int hpet_rtc_dropped_irq(void);
-extern int hpet_rtc_timer_init(void);
-#endif /* CONFIG_HPET_EMULATE_RTC */
-
-#endif
+#include <asm-i386/hpet.h>
Index: linux-2.6.22-rc4-mm/include/asm-i386/hpet.h
===================================================================
--- linux-2.6.22-rc4-mm.orig/include/asm-i386/hpet.h 2007-06-23 14:38:54.000000000 +0200
+++ linux-2.6.22-rc4-mm/include/asm-i386/hpet.h 2007-06-23 14:39:00.000000000 +0200
@@ -4,112 +4,87 @@

#ifdef CONFIG_HPET_TIMER

-#include <linux/errno.h>
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/param.h>
-#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/interrupt.h>
-#include <linux/time.h>
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-
-#include <asm/io.h>
-#include <asm/smp.h>
-#include <asm/irq.h>
-#include <asm/msr.h>
-#include <asm/delay.h>
-#include <asm/mpspec.h>
-#include <asm/uaccess.h>
-#include <asm/processor.h>
-
-#include <linux/timex.h>
-
/*
* Documentation on HPET can be found at:
* http://www.intel.com/ial/home/sp/pcmmspec.htm
* ftp://download.intel.com/ial/home/sp/mmts098.pdf
*/

-#define HPET_MMAP_SIZE 1024
+#define HPET_MMAP_SIZE 1024

-#define HPET_ID 0x000
-#define HPET_PERIOD 0x004
-#define HPET_CFG 0x010
-#define HPET_STATUS 0x020
-#define HPET_COUNTER 0x0f0
-#define HPET_T0_CFG 0x100
-#define HPET_T0_CMP 0x108
-#define HPET_T0_ROUTE 0x110
-#define HPET_T1_CFG 0x120
-#define HPET_T1_CMP 0x128
-#define HPET_T1_ROUTE 0x130
-#define HPET_T2_CFG 0x140
-#define HPET_T2_CMP 0x148
-#define HPET_T2_ROUTE 0x150
-
-#define HPET_ID_LEGSUP 0x00008000
-#define HPET_ID_NUMBER 0x00001f00
-#define HPET_ID_REV 0x000000ff
+#define HPET_ID 0x000
+#define HPET_PERIOD 0x004
+#define HPET_CFG 0x010
+#define HPET_STATUS 0x020
+#define HPET_COUNTER 0x0f0
+#define HPET_T0_CFG 0x100
+#define HPET_T0_CMP 0x108
+#define HPET_T0_ROUTE 0x110
+#define HPET_T1_CFG 0x120
+#define HPET_T1_CMP 0x128
+#define HPET_T1_ROUTE 0x130
+#define HPET_T2_CFG 0x140
+#define HPET_T2_CMP 0x148
+#define HPET_T2_ROUTE 0x150
+
+#define HPET_ID_REV 0x000000ff
+#define HPET_ID_NUMBER 0x00001f00
+#define HPET_ID_64BIT 0x00002000
+#define HPET_ID_LEGSUP 0x00008000
+#define HPET_ID_VENDOR 0xffff0000
#define HPET_ID_NUMBER_SHIFT 8
+#define HPET_ID_VENDOR_SHIFT 16
+
+#define HPET_ID_VENDOR_8086 0x8086

-#define HPET_CFG_ENABLE 0x001
-#define HPET_CFG_LEGACY 0x002
+#define HPET_CFG_ENABLE 0x001
+#define HPET_CFG_LEGACY 0x002
#define HPET_LEGACY_8254 2
#define HPET_LEGACY_RTC 8

-#define HPET_TN_ENABLE 0x004
-#define HPET_TN_PERIODIC 0x008
-#define HPET_TN_PERIODIC_CAP 0x010
-#define HPET_TN_SETVAL 0x040
-#define HPET_TN_32BIT 0x100
-
-/* Use our own asm for 64 bit multiply/divide */
-#define ASM_MUL64_REG(eax_out,edx_out,reg_in,eax_in) \
- __asm__ __volatile__("mull %2" \
- :"=a" (eax_out), "=d" (edx_out) \
- :"r" (reg_in), "0" (eax_in))
-
-#define ASM_DIV64_REG(eax_out,edx_out,reg_in,eax_in,edx_in) \
- __asm__ __volatile__("divl %2" \
- :"=a" (eax_out), "=d" (edx_out) \
- :"r" (reg_in), "0" (eax_in), "1" (edx_in))
+#define HPET_TN_LEVEL 0x0002
+#define HPET_TN_ENABLE 0x0004
+#define HPET_TN_PERIODIC 0x0008
+#define HPET_TN_PERIODIC_CAP 0x0010
+#define HPET_TN_64BIT_CAP 0x0020
+#define HPET_TN_SETVAL 0x0040
+#define HPET_TN_32BIT 0x0100
+#define HPET_TN_ROUTE 0x3e00
+#define HPET_TN_FSB 0x4000
+#define HPET_TN_FSB_CAP 0x8000
+#define HPET_TN_ROUTE_SHIFT 9

-#define KERNEL_TICK_USEC (1000000UL/HZ) /* tick value in microsec */
/* Max HPET Period is 10^8 femto sec as in HPET spec */
-#define HPET_MAX_PERIOD (100000000UL)
+#define HPET_MAX_PERIOD 100000000UL
/*
* Min HPET period is 10^5 femto sec just for safety. If it is less than this,
* then 32 bit HPET counter wrapsaround in less than 0.5 sec.
*/
-#define HPET_MIN_PERIOD (100000UL)
-#define HPET_TICK_RATE (HZ * 100000UL)
+#define HPET_MIN_PERIOD 100000UL

-extern unsigned long hpet_address; /* hpet memory map physical address */
+/* hpet memory map physical address */
+extern unsigned long hpet_address;
extern int is_hpet_enabled(void);
+extern int hpet_enable(void);

#ifdef CONFIG_X86_64
-extern unsigned long hpet_tick; /* hpet clks count per tick */
-extern int hpet_use_timer;
-extern int hpet_rtc_timer_init(void);
-extern int hpet_enable(void);
-extern int is_hpet_capable(void);
-extern int hpet_readl(unsigned long a);
-#else
-extern int hpet_enable(void);
+/* hpet_readl/writel defines */
+#include <asm/vsyscall.h>
#endif

#ifdef CONFIG_HPET_EMULATE_RTC
+
+#include <linux/interrupt.h>
+
extern int hpet_mask_rtc_irq_bit(unsigned long bit_mask);
extern int hpet_set_rtc_irq_bit(unsigned long bit_mask);
-extern int hpet_set_alarm_time(unsigned char hrs, unsigned char min, unsigned char sec);
+extern int hpet_set_alarm_time(unsigned char hrs, unsigned char min,
+ unsigned char sec);
extern int hpet_set_periodic_freq(unsigned long freq);
extern int hpet_rtc_dropped_irq(void);
extern int hpet_rtc_timer_init(void);
extern irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id);
+
#endif /* CONFIG_HPET_EMULATE_RTC */

#else
Index: linux-2.6.22-rc4-mm/arch/i386/kernel/hpet.c
===================================================================
--- linux-2.6.22-rc4-mm.orig/arch/i386/kernel/hpet.c 2007-06-23 14:38:59.000000000 +0200
+++ linux-2.6.22-rc4-mm/arch/i386/kernel/hpet.c 2007-06-23 14:39:00.000000000 +0200
@@ -1,11 +1,14 @@
#include <linux/clocksource.h>
#include <linux/clockchips.h>
+#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/hpet.h>
#include <linux/init.h>
+#include <linux/ioport.h>
#include <linux/sysdev.h>
#include <linux/pm.h>

+#include <asm/fixmap.h>
#include <asm/hpet.h>
#include <asm/io.h>

@@ -21,6 +24,27 @@ extern struct clock_event_device *global
* HPET address is set in acpi/boot.c, when an ACPI entry exists
*/
unsigned long hpet_address;
+
+#ifdef CONFIG_X86_64
+
+#include <asm/pgtable.h>
+#include <asm/vsyscall.h>
+
+static inline void hpet_set_mapping(void)
+{
+ set_fixmap_nocache(FIX_HPET_BASE, hpet_address);
+ __set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE);
+}
+
+static inline void __iomem *hpet_get_virt_address(void)
+{
+ return (void __iomem *)fix_to_virt(FIX_HPET_BASE);
+}
+
+static inline void hpet_clear_mapping(void) { }
+
+#else
+
static void __iomem * hpet_virt_address;

static inline unsigned long hpet_readl(unsigned long a)
@@ -33,6 +57,23 @@ static inline void hpet_writel(unsigned
writel(d, hpet_virt_address + a);
}

+static inline void hpet_set_mapping(void)
+{
+ hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
+}
+
+static inline void __iomem *hpet_get_virt_address(void)
+{
+ return hpet_virt_address;
+}
+
+static inline void hpet_clear_mapping(void)
+{
+ iounmap(hpet_virt_address);
+ hpet_virt_address = NULL;
+}
+#endif
+
/*
* HPET command line enable / disable
*/
@@ -73,7 +114,7 @@ int is_hpet_enabled(void)
#ifdef CONFIG_HPET
static void hpet_reserve_platform_timers(unsigned long id)
{
- struct hpet __iomem *hpet = hpet_virt_address;
+ struct hpet __iomem *hpet = hpet_get_virt_address();
struct hpet_timer __iomem *timer = &hpet->hpet_timers[2];
unsigned int nrtimers, i;
struct hpet_data hd;
@@ -82,7 +123,7 @@ static void hpet_reserve_platform_timers

memset(&hd, 0, sizeof (hd));
hd.hd_phys_address = hpet_address;
- hd.hd_address = hpet_virt_address;
+ hd.hd_address = hpet;
hd.hd_nirqs = nrtimers;
hd.hd_flags = HPET_DATA_PLATFORM;
hpet_reserve_timer(&hd, 0);
@@ -237,7 +278,7 @@ int __init hpet_enable(void)
if (!is_hpet_capable())
return 0;

- hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
+ hpet_set_mapping();

/*
* Read the period and check for a sane value:
@@ -333,8 +374,7 @@ int __init hpet_enable(void)
return 0;

out_nohpet:
- iounmap(hpet_virt_address);
- hpet_virt_address = NULL;
+ hpet_clear_mapping();
boot_hpet_disable = 1;
return 0;
}
Index: linux-2.6.22-rc4-mm/arch/x86_64/kernel/smpboot.c
===================================================================
--- linux-2.6.22-rc4-mm.orig/arch/x86_64/kernel/smpboot.c 2007-06-23 14:38:54.000000000 +0200
+++ linux-2.6.22-rc4-mm/arch/x86_64/kernel/smpboot.c 2007-06-23 14:39:00.000000000 +0200
@@ -223,8 +223,6 @@ void __cpuinit smp_callin(void)
local_irq_disable();
Dprintk("Stack at about %p\n",&cpuid);

- disable_APIC_timer();
-
/*
* Save our processor parameters
*/
@@ -348,8 +346,6 @@ void __cpuinit start_secondary(void)
enable_8259A_irq(0);
}

- enable_APIC_timer();
-
/*
* The sibling maps must be set before turing the online map on for
* this cpu
Index: linux-2.6.22-rc4-mm/include/asm-x86_64/i8253.h
===================================================================
--- linux-2.6.22-rc4-mm.orig/include/asm-x86_64/i8253.h 2007-06-23 14:38:58.000000000 +0200
+++ linux-2.6.22-rc4-mm/include/asm-x86_64/i8253.h 2007-06-23 14:39:00.000000000 +0200
@@ -1,6 +1,2 @@
-#ifndef __ASM_I8253_H__
-#define __ASM_I8253_H__
-
-extern spinlock_t i8253_lock;
-
-#endif /* __ASM_I8253_H__ */
+#include <asm-i386/i8253.h>
+#include <asm/8253pit.h>
Index: linux-2.6.22-rc4-mm/include/asm-x86_64/proto.h
===================================================================
--- linux-2.6.22-rc4-mm.orig/include/asm-x86_64/proto.h 2007-06-23 14:38:54.000000000 +0200
+++ linux-2.6.22-rc4-mm/include/asm-x86_64/proto.h 2007-06-23 14:39:00.000000000 +0200
@@ -51,9 +51,6 @@ extern void reserve_bootmem_generic(unsi

extern void load_gs_index(unsigned gs);

-extern void stop_timer_interrupt(void);
-extern void main_timer_handler(void);
-
extern unsigned long end_pfn_map;

extern void show_trace(struct task_struct *, struct pt_regs *, unsigned long * rsp);
Index: linux-2.6.22-rc4-mm/arch/i386/kernel/i8253.c
===================================================================
--- linux-2.6.22-rc4-mm.orig/arch/i386/kernel/i8253.c 2007-06-23 14:38:59.000000000 +0200
+++ linux-2.6.22-rc4-mm/arch/i386/kernel/i8253.c 2007-06-23 14:39:00.000000000 +0200
@@ -120,6 +120,7 @@ void __init setup_pit_timer(void)
global_clock_event = &pit_clockevent;
}

+#ifndef CONFIG_X86_64
/*
* Since the PIT overflows every tick, its not very useful
* to just read by itself. So use jiffies to emulate a free
@@ -204,3 +205,5 @@ static int __init init_pit_clocksource(v
return clocksource_register(&clocksource_pit);
}
arch_initcall(init_pit_clocksource);
+
+#endif
Index: linux-2.6.22-rc4-mm/arch/x86_64/kernel/tsc.c
===================================================================
--- linux-2.6.22-rc4-mm.orig/arch/x86_64/kernel/tsc.c 2007-06-23 14:38:59.000000000 +0200
+++ linux-2.6.22-rc4-mm/arch/x86_64/kernel/tsc.c 2007-06-23 14:39:00.000000000 +0200
@@ -6,7 +6,9 @@
#include <linux/time.h>
#include <linux/acpi.h>
#include <linux/cpufreq.h>
+#include <linux/acpi_pmtmr.h>

+#include <asm/hpet.h>
#include <asm/timex.h>

static int notsc __initdata = 0;
@@ -90,6 +92,94 @@ core_initcall(cpufreq_tsc);

#endif

+#define MAX_RETRIES 5
+#define SMI_TRESHOLD 50000
+
+/*
+ * Read TSC and the reference counters. Take care of SMI disturbance
+ */
+static unsigned long __init tsc_read_refs(unsigned long *pm,
+ unsigned long *hpet)
+{
+ unsigned long t1, t2;
+ int i;
+
+ for (i = 0; i < MAX_RETRIES; i++) {
+ t1 = get_cycles_sync();
+ if (hpet)
+ *hpet = hpet_readl(HPET_COUNTER) & 0xFFFFFFFF;
+ else
+ *pm = acpi_pm_read_early();
+ t2 = get_cycles_sync();
+ if ((t2 - t1) < SMI_TRESHOLD)
+ return t2;
+ }
+ return ULONG_MAX;
+}
+
+/**
+ * tsc_calibrate - calibrate the tsc on boot
+ */
+void __init tsc_calibrate(void)
+{
+ unsigned long flags, tsc1, tsc2, tr1, tr2, pm1, pm2, hpet1, hpet2;
+ int hpet = is_hpet_enabled();
+
+ local_irq_save(flags);
+
+ tsc1 = tsc_read_refs(&pm1, hpet ? &hpet1 : NULL);
+
+ outb((inb(0x61) & ~0x02) | 0x01, 0x61);
+
+ outb(0xb0, 0x43);
+ outb((CLOCK_TICK_RATE / (1000 / 50)) & 0xff, 0x42);
+ outb((CLOCK_TICK_RATE / (1000 / 50)) >> 8, 0x42);
+ tr1 = get_cycles_sync();
+ while ((inb(0x61) & 0x20) == 0);
+ tr2 = get_cycles_sync();
+
+ tsc2 = tsc_read_refs(&pm2, hpet ? &hpet2 : NULL);
+
+ local_irq_restore(flags);
+
+ /*
+ * Preset the result with the raw and inaccurate PIT
+ * calibration value
+ */
+ tsc_khz = (tr2 - tr1) / 50;
+
+ /* hpet or pmtimer available ? */
+ if (!hpet && !pm1 && !pm2) {
+ printk(KERN_INFO "TSC calibrated against PIT\n");
+ return;
+ }
+
+ /* Check, whether the sampling was disturbed by an SMI */
+ if (tsc1 == ULONG_MAX || tsc2 == ULONG_MAX) {
+ printk(KERN_WARNING "TSC calibration disturbed by SMI, "
+ "using PIT calibration result\n");
+ return;
+ }
+
+ tsc2 = (tsc2 - tsc1) * 1000000L;
+
+ if (hpet) {
+ printk(KERN_INFO "TSC calibrated against HPET\n");
+ if (hpet2 < hpet1)
+ hpet2 += 0x100000000;
+ hpet2 -= hpet1;
+ tsc1 = (hpet2 * hpet_readl(HPET_PERIOD)) / 1000000;
+ } else {
+ printk(KERN_INFO "TSC calibrated against PM_TIMER\n");
+ if (pm2 < pm1)
+ pm2 += ACPI_PM_OVRRUN;
+ pm2 -= pm1;
+ tsc1 = (pm2 * 1000000000) / PMTMR_TICKS_PER_SEC;
+ }
+
+ tsc_khz = tsc2 / tsc1;
+}
+
/*
* Make an educated guess if the TSC is trustworthy and synchronized
* over all CPUs.
Index: linux-2.6.22-rc4-mm/include/asm-i386/tsc.h
===================================================================
--- linux-2.6.22-rc4-mm.orig/include/asm-i386/tsc.h 2007-06-23 14:38:54.000000000 +0200
+++ linux-2.6.22-rc4-mm/include/asm-i386/tsc.h 2007-06-23 14:39:00.000000000 +0200
@@ -71,4 +71,8 @@ extern void init_tsc_clocksource(void);
extern void check_tsc_sync_source(int cpu);
extern void check_tsc_sync_target(void);

+#ifdef CONFIG_X86_64
+extern void tsc_calibrate(void);
+#endif
+
#endif
Index: linux-2.6.22-rc4-mm/arch/x86_64/kernel/i8259.c
===================================================================
--- linux-2.6.22-rc4-mm.orig/arch/x86_64/kernel/i8259.c 2007-06-23 14:38:54.000000000 +0200
+++ linux-2.6.22-rc4-mm/arch/x86_64/kernel/i8259.c 2007-06-23 14:39:00.000000000 +0200
@@ -460,47 +460,6 @@ void invalidate_interrupt6(void);
void invalidate_interrupt7(void);
void thermal_interrupt(void);
void threshold_interrupt(void);
-void i8254_timer_resume(void);
-
-static void setup_timer_hardware(void)
-{
- outb_p(0x34,0x43); /* binary, mode 2, LSB/MSB, ch 0 */
- udelay(10);
- outb_p(LATCH & 0xff , 0x40); /* LSB */
- udelay(10);
- outb(LATCH >> 8 , 0x40); /* MSB */
-}
-
-static int timer_resume(struct sys_device *dev)
-{
- setup_timer_hardware();
- return 0;
-}
-
-void i8254_timer_resume(void)
-{
- setup_timer_hardware();
-}
-
-static struct sysdev_class timer_sysclass = {
- set_kset_name("timer_pit"),
- .resume = timer_resume,
-};
-
-static struct sys_device device_timer = {
- .id = 0,
- .cls = &timer_sysclass,
-};
-
-static int __init init_timer_sysfs(void)
-{
- int error = sysdev_class_register(&timer_sysclass);
- if (!error)
- error = sysdev_register(&device_timer);
- return error;
-}
-
-device_initcall(init_timer_sysfs);

void __init init_IRQ(void)
{
@@ -551,12 +510,6 @@ void __init init_IRQ(void)
set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
set_intr_gate(ERROR_APIC_VECTOR, error_interrupt);

- /*
- * Set the clock to HZ Hz, we already have a valid
- * vector now:
- */
- setup_timer_hardware();
-
if (!acpi_ioapic)
setup_irq(2, &irq2);
}
Index: linux-2.6.22-rc4-mm/arch/x86_64/kernel/Makefile
===================================================================
--- linux-2.6.22-rc4-mm.orig/arch/x86_64/kernel/Makefile 2007-06-23 14:38:54.000000000 +0200
+++ linux-2.6.22-rc4-mm/arch/x86_64/kernel/Makefile 2007-06-23 14:39:00.000000000 +0200
@@ -9,7 +9,7 @@ obj-y := process.o signal.o entry.o trap
x8664_ksyms.o i387.o syscall.o vsyscall.o \
setup64.o bootflag.o e820.o reboot.o quirks.o i8237.o \
pci-dma.o pci-nommu.o alternative.o hpet.o tsc.o bugs.o \
- perfctr-watchdog.o sched-clock.o
+ perfctr-watchdog.o sched-clock.o i8253.o

obj-$(CONFIG_STACKTRACE) += stacktrace.o
obj-$(CONFIG_X86_MCE) += mce.o therm_throt.o
@@ -49,6 +49,8 @@ obj-y += pcspeaker.o

CFLAGS_vsyscall.o := $(PROFILING) -g0

+i8253-y += ../../i386/kernel/i8253.o
+hpet-y += ../../i386/kernel/hpet.o
therm_throt-y += ../../i386/kernel/cpu/mcheck/therm_throt.o
bootflag-y += ../../i386/kernel/bootflag.o
legacy_serial-y += ../../i386/kernel/legacy_serial.o
Index: linux-2.6.22-rc4-mm/arch/x86_64/kernel/apic.c
===================================================================
--- linux-2.6.22-rc4-mm.orig/arch/x86_64/kernel/apic.c 2007-06-23 14:39:00.000000000 +0200
+++ linux-2.6.22-rc4-mm/arch/x86_64/kernel/apic.c 2007-06-23 14:39:00.000000000 +0200
@@ -25,6 +25,8 @@
#include <linux/sysdev.h>
#include <linux/module.h>
#include <linux/ioport.h>
+#include <linux/clockchips.h>
+#include <linux/acpi_pmtmr.h>

#include <asm/atomic.h>
#include <asm/smp.h>
@@ -38,10 +40,10 @@
#include <asm/timex.h>
#include <asm/hpet.h>
#include <asm/apic.h>
+#include <asm/i8253.h>

int apic_mapped;
int apic_verbosity;
-int apic_runs_main_timer;
int apic_calibrate_pmtmr __initdata;

int disable_apic_timer __initdata;
@@ -50,20 +52,36 @@ int disable_apic_timer __initdata;
int local_apic_timer_c2_ok;
EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);

+/* Local APIC timer verification ok */
+static int local_apic_timer_verify_ok;
+
static struct resource *ioapic_resources;
static struct resource lapic_resource = {
.name = "Local APIC",
.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
};

-/*
- * cpu_mask that denotes the CPUs that needs timer interrupt coming in as
- * IPIs in place of local APIC timers
- */
-static cpumask_t timer_interrupt_broadcast_ipi_mask;
+static unsigned int calibration_result;

-/* Using APIC to generate smp_local_timer_interrupt? */
-int using_apic_timer __read_mostly = 0;
+static int lapic_next_event(unsigned long delta,
+ struct clock_event_device *evt);
+static void lapic_timer_setup(enum clock_event_mode mode,
+ struct clock_event_device *evt);
+
+static void lapic_timer_broadcast(cpumask_t mask);
+
+static struct clock_event_device lapic_clockevent = {
+ .name = "lapic",
+ .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT
+ | CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY,
+ .shift = 32,
+ .set_mode = lapic_timer_setup,
+ .set_next_event = lapic_next_event,
+ .broadcast = lapic_timer_broadcast,
+ .rating = 100,
+ .irq = -1,
+};
+static DEFINE_PER_CPU(struct clock_event_device, lapic_events);

static void apic_pm_activate(void);

@@ -92,8 +110,9 @@ unsigned int safe_apic_wait_icr_idle(voi
void enable_NMI_through_LVT0 (void * dummy)
{
unsigned int v;
-
- v = APIC_DM_NMI; /* unmask and set to NMI */
+
+ /* unmask and set to NMI */
+ v = APIC_DM_NMI;
apic_write(APIC_LVT0, v);
}

@@ -120,7 +139,7 @@ void ack_bad_irq(unsigned int irq)
* holds up an irq slot - in excessive cases (when multiple
* unexpected vectors occur) that might lock up the APIC
* completely.
- * But don't ack when the APIC is disabled. -AK
+ * But don't ack when the APIC is disabled. -AK
*/
if (!disable_apic)
ack_APIC_irq();
@@ -616,7 +635,7 @@ early_param("apic", apic_set_verbosity);
* Detect and enable local APICs on non-SMP boards.
* Original code written by Keir Fraser.
* On AMD64 we trust the BIOS - if it says no APIC it is likely
- * not correctly set up (usually the APIC timer won't work etc.)
+ * not correctly set up (usually the APIC timer won't work etc.)
*/

static int __init detect_init_APIC (void)
@@ -759,14 +778,14 @@ void __init init_apic_mappings(void)

#define APIC_DIVISOR 16

-static void __setup_APIC_LVTT(unsigned int clocks)
+static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
{
unsigned int lvtt_value, tmp_value;
- int cpu = smp_processor_id();
-
- lvtt_value = APIC_LVT_TIMER_PERIODIC | LOCAL_TIMER_VECTOR;

- if (cpu_isset(cpu, timer_interrupt_broadcast_ipi_mask))
+ lvtt_value = LOCAL_TIMER_VECTOR;
+ if (!oneshot)
+ lvtt_value |= APIC_LVT_TIMER_PERIODIC;
+ if (!irqen)
lvtt_value |= APIC_LVT_MASKED;

apic_write(APIC_LVTT, lvtt_value);
@@ -779,211 +798,298 @@ static void __setup_APIC_LVTT(unsigned i
& ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE))
| APIC_TDR_DIV_16);

- apic_write(APIC_TMICT, clocks/APIC_DIVISOR);
+ if (!oneshot)
+ apic_write(APIC_TMICT, clocks/APIC_DIVISOR);
}

-static void setup_APIC_timer(unsigned int clocks)
+static int lapic_next_event(unsigned long delta,
+ struct clock_event_device *evt)
+{
+ apic_write(APIC_TMICT, delta);
+ return 0;
+}
+
+static void lapic_timer_setup(enum clock_event_mode mode,
+ struct clock_event_device *evt)
{
unsigned long flags;
+ unsigned int v;
+
+ /* Lapic used for broadcast ? */
+ if (!local_apic_timer_verify_ok)
+ return;

local_irq_save(flags);

- /* wait for irq slice */
- if (hpet_address && hpet_use_timer) {
- int trigger = hpet_readl(HPET_T0_CMP);
- while (hpet_readl(HPET_COUNTER) >= trigger)
- /* do nothing */ ;
- while (hpet_readl(HPET_COUNTER) < trigger)
- /* do nothing */ ;
- } else {
- int c1, c2;
- outb_p(0x00, 0x43);
- c2 = inb_p(0x40);
- c2 |= inb_p(0x40) << 8;
- do {
- c1 = c2;
- outb_p(0x00, 0x43);
- c2 = inb_p(0x40);
- c2 |= inb_p(0x40) << 8;
- } while (c2 - c1 < 300);
- }
- __setup_APIC_LVTT(clocks);
- /* Turn off PIT interrupt if we use APIC timer as main timer.
- Only works with the PM timer right now
- TBD fix it for HPET too. */
- if ((pmtmr_ioport != 0) &&
- smp_processor_id() == boot_cpu_id &&
- apic_runs_main_timer == 1 &&
- !cpu_isset(boot_cpu_id, timer_interrupt_broadcast_ipi_mask)) {
- stop_timer_interrupt();
- apic_runs_main_timer++;
+ switch (mode) {
+ case CLOCK_EVT_MODE_PERIODIC:
+ case CLOCK_EVT_MODE_ONESHOT:
+ __setup_APIC_LVTT(calibration_result,
+ mode != CLOCK_EVT_MODE_PERIODIC, 1);
+ break;
+ case CLOCK_EVT_MODE_UNUSED:
+ case CLOCK_EVT_MODE_SHUTDOWN:
+ v = apic_read(APIC_LVTT);
+ v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
+ apic_write(APIC_LVTT, v);
+ break;
+ case CLOCK_EVT_MODE_RESUME:
+ /* Nothing to do here */
+ break;
}
+
local_irq_restore(flags);
}

/*
- * In this function we calibrate APIC bus clocks to the external
- * timer. Unfortunately we cannot use jiffies and the timer irq
- * to calibrate, since some later bootup code depends on getting
- * the first irq? Ugh.
- *
- * We want to do the calibration only once since we
- * want to have local timer irqs syncron. CPUs connected
- * by the same APIC bus have the very same bus frequency.
- * And we want to have irqs off anyways, no accidental
- * APIC irq that way.
+ * Local APIC timer broadcast function
*/
-
-#define TICK_COUNT 100000000
-
-static int __init calibrate_APIC_clock(void)
+static void lapic_timer_broadcast(cpumask_t mask)
{
- unsigned apic, apic_start;
- unsigned long tsc, tsc_start;
- int result;
- /*
- * Put whatever arbitrary (but long enough) timeout
- * value into the APIC clock, we just want to get the
- * counter running for calibration.
- */
- __setup_APIC_LVTT(4000000000);
-
- apic_start = apic_read(APIC_TMCCT);
-#ifdef CONFIG_X86_PM_TIMER
- if (apic_calibrate_pmtmr && pmtmr_ioport) {
- pmtimer_wait(5000); /* 5ms wait */
- apic = apic_read(APIC_TMCCT);
- result = (apic_start - apic) * 1000L / 5;
- } else
+#ifdef CONFIG_SMP
+ send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
#endif
- {
- rdtscll(tsc_start);
+}

- do {
- apic = apic_read(APIC_TMCCT);
- rdtscll(tsc);
- } while ((tsc - tsc_start) < TICK_COUNT &&
- (apic_start - apic) < TICK_COUNT);
+static void __devinit setup_APIC_timer(void)
+{
+ struct clock_event_device *levt = &__get_cpu_var(lapic_events);

- result = (apic_start - apic) * 1000L * tsc_khz /
- (tsc - tsc_start);
- }
- printk("result %d\n", result);
+ memcpy(levt, &lapic_clockevent, sizeof(*levt));
+ levt->cpumask = cpumask_of_cpu(smp_processor_id());
+
+ clockevents_register_device(levt);
+}
+
+/*
+ * In this functions we calibrate APIC bus clocks to the external timer.
+ *
+ * We want to do the calibration only once since we want to have local timer
+ * irqs syncron. CPUs connected by the same APIC bus have the very same bus
+ * frequency.
+ *
+ * This was previously done by reading the PIT/HPET and waiting for a wrap
+ * around to find out, that a tick has elapsed. I have a box, where the PIT
+ * readout is broken, so it never gets out of the wait loop again. This was
+ * also reported by others.
+ *
+ * Monitoring the jiffies value is inaccurate and the clockevents
+ * infrastructure allows us to do a simple substitution of the interrupt
+ * handler.
+ *
+ * The calibration routine also uses the pm_timer when possible, as the PIT
+ * happens to run way too slow (factor 2.3 on my VAIO CoreDuo, which goes
+ * back to normal later in the boot process).
+ */

+#define LAPIC_CAL_LOOPS (HZ/10)

- printk(KERN_INFO "Detected %d.%03d MHz APIC timer.\n",
- result / 1000 / 1000, result / 1000 % 1000);
+static __initdata int lapic_cal_loops = -1;
+static __initdata long lapic_cal_t1, lapic_cal_t2;
+static __initdata unsigned long long lapic_cal_tsc1, lapic_cal_tsc2;
+static __initdata unsigned long lapic_cal_pm1, lapic_cal_pm2;
+static __initdata unsigned long lapic_cal_j1, lapic_cal_j2;

- return result * APIC_DIVISOR / HZ;
+/*
+ * Temporary interrupt handler.
+ */
+static void __init lapic_cal_handler(struct clock_event_device *dev)
+{
+ unsigned long long tsc = 0;
+ long tapic = apic_read(APIC_TMCCT);
+ unsigned long pm = acpi_pm_read_early();
+
+ if (cpu_has_tsc)
+ rdtscll(tsc);
+
+ switch (lapic_cal_loops++) {
+ case 0:
+ lapic_cal_t1 = tapic;
+ lapic_cal_tsc1 = tsc;
+ lapic_cal_pm1 = pm;
+ lapic_cal_j1 = jiffies;
+ break;
+
+ case LAPIC_CAL_LOOPS:
+ lapic_cal_t2 = tapic;
+ lapic_cal_tsc2 = tsc;
+ if (pm < lapic_cal_pm1)
+ pm += ACPI_PM_OVRRUN;
+ lapic_cal_pm2 = pm;
+ lapic_cal_j2 = jiffies;
+ break;
+ }
}

-static unsigned int calibration_result;
-
void __init setup_boot_APIC_clock (void)
{
- if (disable_apic_timer) {
- printk(KERN_INFO "Disabling APIC timer\n");
- return;
- }
+ struct clock_event_device *levt = &__get_cpu_var(lapic_events);
+ const long pm_100ms = PMTMR_TICKS_PER_SEC/10;
+ const long pm_thresh = pm_100ms/100;
+ void (*real_handler)(struct clock_event_device *dev);
+ unsigned long deltaj;
+ long delta, deltapm;
+ int pm_referenced = 0;
+
+ /*
+ * The local apic timer can be disabled via the kernel
+ * commandline or from the test above. Register the lapic
+ * timer as a dummy clock event source on SMP systems, so the
+ * broadcast mechanism is used. On UP systems simply ignore it.
+ */
+ if (disable_apic_timer) {
+ printk(KERN_INFO "Disabling APIC timer\n");
+ /* No broadcast on UP ! */
+ if (num_possible_cpus() > 1)
+ setup_APIC_timer();
+ return;
+ }

printk(KERN_INFO "Using local APIC timer interrupts.\n");
- using_apic_timer = 1;

- local_irq_disable();
+ /* Replace the global interrupt handler */
+ real_handler = global_clock_event->event_handler;
+ global_clock_event->event_handler = lapic_cal_handler;

- calibration_result = calibrate_APIC_clock();
/*
- * Now set up the timer for real.
+ * Setup the APIC counter to 1e9. There is no way the lapic
+ * can underflow in the 100ms detection time frame
*/
- setup_APIC_timer(calibration_result);
+ __setup_APIC_LVTT(1000000000, 0, 0);

+ /* Let the interrupts run */
local_irq_enable();
-}

-void __cpuinit setup_secondary_APIC_clock(void)
-{
- local_irq_disable(); /* FIXME: Do we need this? --RR */
- setup_APIC_timer(calibration_result);
- local_irq_enable();
-}
+ while (lapic_cal_loops <= LAPIC_CAL_LOOPS)
+ cpu_relax();

-void disable_APIC_timer(void)
-{
- if (using_apic_timer) {
- unsigned long v;
+ local_irq_disable();

- v = apic_read(APIC_LVTT);
- /*
- * When an illegal vector value (0-15) is written to an LVT
- * entry and delivery mode is Fixed, the APIC may signal an
- * illegal vector error, with out regard to whether the mask
- * bit is set or whether an interrupt is actually seen on input.
- *
- * Boot sequence might call this function when the LVTT has
- * '0' vector value. So make sure vector field is set to
- * valid value.
- */
- v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
- apic_write(APIC_LVTT, v);
+ /* Restore the real event handler */
+ global_clock_event->event_handler = real_handler;
+
+ /* Build delta t1-t2 as apic timer counts down */
+ delta = lapic_cal_t1 - lapic_cal_t2;
+ apic_printk(APIC_VERBOSE, "... lapic delta = %ld\n", delta);
+
+ /* Check, if the PM timer is available */
+ deltapm = lapic_cal_pm2 - lapic_cal_pm1;
+ apic_printk(APIC_VERBOSE, "... PM timer delta = %ld\n", deltapm);
+
+ if (deltapm) {
+ unsigned long mult;
+ u64 res;
+
+ mult = clocksource_hz2mult(PMTMR_TICKS_PER_SEC, 22);
+
+ if (deltapm > (pm_100ms - pm_thresh) &&
+ deltapm < (pm_100ms + pm_thresh)) {
+ apic_printk(APIC_VERBOSE, "... PM timer result ok\n");
+ } else {
+ res = (((u64) deltapm) * mult) >> 22;
+ do_div(res, 1000000);
+ printk(KERN_WARNING "APIC calibration not consistent "
+ "with PM Timer: %ldms instead of 100ms\n",
+ (long)res);
+ /* Correct the lapic counter value */
+ res = (((u64) delta ) * pm_100ms);
+ do_div(res, deltapm);
+ printk(KERN_INFO "APIC delta adjusted to PM-Timer: "
+ "%lu (%ld)\n", (unsigned long) res, delta);
+ delta = (long) res;
+ }
+ pm_referenced = 1;
}
-}

-void enable_APIC_timer(void)
-{
- int cpu = smp_processor_id();
+ /* Calculate the scaled math multiplication factor */
+ lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS, 32);
+ lapic_clockevent.max_delta_ns =
+ clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
+ lapic_clockevent.min_delta_ns =
+ clockevent_delta2ns(0xF, &lapic_clockevent);

- if (using_apic_timer &&
- !cpu_isset(cpu, timer_interrupt_broadcast_ipi_mask)) {
- unsigned long v;
+ calibration_result = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;

- v = apic_read(APIC_LVTT);
- apic_write(APIC_LVTT, v & ~APIC_LVT_MASKED);
+ apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta);
+ apic_printk(APIC_VERBOSE, "..... mult: %ld\n", lapic_clockevent.mult);
+ apic_printk(APIC_VERBOSE, "..... calibration result: %u\n",
+ calibration_result);
+
+ if (cpu_has_tsc) {
+ delta = (long)(lapic_cal_tsc2 - lapic_cal_tsc1);
+ apic_printk(APIC_VERBOSE, "..... CPU clock speed is "
+ "%ld.%04ld MHz.\n",
+ (delta / LAPIC_CAL_LOOPS) / (1000000 / HZ),
+ (delta / LAPIC_CAL_LOOPS) % (1000000 / HZ));
}
-}

-void switch_APIC_timer_to_ipi(void *cpumask)
-{
- cpumask_t mask = *(cpumask_t *)cpumask;
- int cpu = smp_processor_id();
+ apic_printk(APIC_VERBOSE, "..... host bus clock speed is "
+ "%u.%04u MHz.\n",
+ calibration_result / (1000000 / HZ),
+ calibration_result % (1000000 / HZ));

- if (cpu_isset(cpu, mask) &&
- !cpu_isset(cpu, timer_interrupt_broadcast_ipi_mask)) {
- disable_APIC_timer();
- cpu_set(cpu, timer_interrupt_broadcast_ipi_mask);
- }
-}
-EXPORT_SYMBOL(switch_APIC_timer_to_ipi);
+ local_apic_timer_verify_ok = 1;

-void smp_send_timer_broadcast_ipi(void)
-{
- int cpu = smp_processor_id();
- cpumask_t mask;
+ /* We trust the pm timer based calibration */
+ if (!pm_referenced) {
+ apic_printk(APIC_VERBOSE, "... verify APIC timer\n");

- cpus_and(mask, cpu_online_map, timer_interrupt_broadcast_ipi_mask);
+ /*
+ * Setup the apic timer manually
+ */
+ levt->event_handler = lapic_cal_handler;
+ lapic_timer_setup(CLOCK_EVT_MODE_PERIODIC, levt);
+ lapic_cal_loops = -1;

- if (cpu_isset(cpu, mask)) {
- cpu_clear(cpu, mask);
- add_pda(apic_timer_irqs, 1);
- smp_local_timer_interrupt();
- }
+ /* Let the interrupts run */
+ local_irq_enable();
+
+ while (lapic_cal_loops <= LAPIC_CAL_LOOPS)
+ cpu_relax();
+
+ local_irq_disable();
+
+ /* Stop the lapic timer */
+ lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, levt);
+
+ local_irq_enable();

- if (!cpus_empty(mask)) {
- send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
+ /* Jiffies delta */
+ deltaj = lapic_cal_j2 - lapic_cal_j1;
+ apic_printk(APIC_VERBOSE, "... jiffies delta = %lu\n", deltaj);
+
+ /* Check, if the jiffies result is consistent */
+ if (deltaj >= LAPIC_CAL_LOOPS-2 && deltaj <= LAPIC_CAL_LOOPS+2)
+ apic_printk(APIC_VERBOSE, "... jiffies result ok\n");
+ else
+ local_apic_timer_verify_ok = 0;
+ } else
+ local_irq_enable();
+
+ if (!local_apic_timer_verify_ok) {
+ printk(KERN_WARNING
+ "APIC timer disabled due to verification failure.\n");
+ /* No broadcast on UP ! */
+ if (num_possible_cpus() == 1)
+ return;
+ } else {
+ /*
+ * If nmi_watchdog is set to IO_APIC, we need the
+ * PIT/HPET going. Otherwise register lapic as a dummy
+ * device.
+ */
+ if (nmi_watchdog != NMI_IO_APIC)
+ lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
}
+
+ /* Setup the lapic or request the broadcast */
+ setup_APIC_timer();
}

-void switch_ipi_to_APIC_timer(void *cpumask)
+void __cpuinit setup_secondary_APIC_clock(void)
{
- cpumask_t mask = *(cpumask_t *)cpumask;
- int cpu = smp_processor_id();
-
- if (cpu_isset(cpu, mask) &&
- cpu_isset(cpu, timer_interrupt_broadcast_ipi_mask)) {
- cpu_clear(cpu, timer_interrupt_broadcast_ipi_mask);
- enable_APIC_timer();
- }
+ setup_APIC_timer();
}
-EXPORT_SYMBOL(switch_ipi_to_APIC_timer);

int setup_profiling_timer(unsigned int multiplier)
{
@@ -995,11 +1101,10 @@ void setup_APIC_extended_lvt(unsigned ch
{
unsigned long reg = (lvt_off << 4) + K8_APIC_EXT_LVT_BASE;
unsigned int v = (mask << 16) | (msg_type << 8) | vector;
+
apic_write(reg, v);
}

-#undef APIC_DIVISOR
-
/*
* Local timer interrupt handler. It does both profiling and
* process statistics/rescheduling.
@@ -1010,24 +1115,36 @@ void setup_APIC_extended_lvt(unsigned ch
* value into /proc/profile.
*/

-void smp_local_timer_interrupt(void)
+void local_apic_timer_interrupt(void)
{
- profile_tick(CPU_PROFILING);
-#ifdef CONFIG_SMP
- update_process_times(user_mode(get_irq_regs()));
-#endif
- if (apic_runs_main_timer > 1 && smp_processor_id() == boot_cpu_id)
- main_timer_handler();
+ int cpu = smp_processor_id();
+ struct clock_event_device *evt = &per_cpu(lapic_events, cpu);
+
/*
- * We take the 'long' return path, and there every subsystem
- * grabs the appropriate locks (kernel lock/ irq lock).
- *
- * We might want to decouple profiling from the 'long path',
- * and do the profiling totally in assembly.
+ * Normally we should not be here till LAPIC has been initialized but
+ * in some cases like kdump, its possible that there is a pending LAPIC
+ * timer interrupt from previous kernel's context and is delivered in
+ * new kernel the moment interrupts are enabled.
*
- * Currently this isn't too much of an issue (performance wise),
- * we can take more than 100K local irqs per second on a 100 MHz P5.
+ * Interrupts are enabled early and LAPIC is setup much later, hence
+ * its possible that when we get here evt->event_handler is NULL.
+ * Check for event_handler being NULL and discard the interrupt as
+ * spurious.
+ */
+ if (!evt->event_handler) {
+ printk(KERN_WARNING
+ "Spurious LAPIC timer interrupt on cpu %d\n", cpu);
+ /* Switch it off */
+ lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt);
+ return;
+ }
+
+ /*
+ * the NMI deadlock-detector uses this.
*/
+ add_pda(apic_timer_irqs, 1);
+
+ evt->event_handler(evt);
}

/*
@@ -1043,11 +1160,6 @@ void smp_apic_timer_interrupt(struct pt_
struct pt_regs *old_regs = set_irq_regs(regs);

/*
- * the NMI deadlock-detector uses this.
- */
- add_pda(apic_timer_irqs, 1);
-
- /*
* NOTE! We'd better ACK the irq immediately,
* because timer handling can be slow.
*/
@@ -1059,7 +1171,7 @@ void smp_apic_timer_interrupt(struct pt_
*/
exit_idle();
irq_enter();
- smp_local_timer_interrupt();
+ local_apic_timer_interrupt();
irq_exit();
set_irq_regs(old_regs);
}
@@ -1127,21 +1239,6 @@ asmlinkage void smp_spurious_interrupt(v
v = apic_read(APIC_ISR + ((SPURIOUS_APIC_VECTOR & ~0x1f) >> 1));
if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f)))
ack_APIC_irq();
-
-#if 0
- static unsigned long last_warning;
- static unsigned long skipped;
-
- /* see sw-dev-man vol 3, chapter 7.4.13.5 */
- if (time_before(last_warning+30*HZ,jiffies)) {
- printk(KERN_INFO "spurious APIC interrupt on CPU#%d, %ld skipped.\n",
- smp_processor_id(), skipped);
- last_warning = jiffies;
- skipped = 0;
- } else {
- skipped++;
- }
-#endif
irq_exit();
}

@@ -1173,11 +1270,11 @@ asmlinkage void smp_error_interrupt(void
7: Illegal register address
*/
printk (KERN_DEBUG "APIC error on CPU%d: %02x(%02x)\n",
- smp_processor_id(), v , v1);
+ smp_processor_id(), v , v1);
irq_exit();
}

-int disable_apic;
+int disable_apic;

/*
* This initializes the IO-APIC and APIC hardware if this is
@@ -1185,11 +1282,11 @@ int disable_apic;
*/
int __init APIC_init_uniprocessor (void)
{
- if (disable_apic) {
+ if (disable_apic) {
printk(KERN_INFO "Apic disabled\n");
- return -1;
+ return -1;
}
- if (!cpu_has_apic) {
+ if (!cpu_has_apic) {
disable_apic = 1;
printk(KERN_INFO "Apic disabled by BIOS\n");
return -1;
@@ -1211,8 +1308,8 @@ int __init APIC_init_uniprocessor (void)
return 0;
}

-static __init int setup_disableapic(char *str)
-{
+static __init int setup_disableapic(char *str)
+{
disable_apic = 1;
clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
return 0;
@@ -1220,10 +1317,10 @@ static __init int setup_disableapic(char
early_param("disableapic", setup_disableapic);

/* same as disableapic, for compatibility */
-static __init int setup_nolapic(char *str)
-{
+static __init int setup_nolapic(char *str)
+{
return setup_disableapic(str);
-}
+}
early_param("nolapic", setup_nolapic);

static int __init parse_lapic_timer_c2_ok(char *arg)
@@ -1233,36 +1330,12 @@ static int __init parse_lapic_timer_c2_o
}
early_param("lapic_timer_c2_ok", parse_lapic_timer_c2_ok);

-static __init int setup_noapictimer(char *str)
-{
+static __init int setup_noapictimer(char *str)
+{
if (str[0] != ' ' && str[0] != 0)
return 0;
disable_apic_timer = 1;
return 1;
-}
-
-static __init int setup_apicmaintimer(char *str)
-{
- apic_runs_main_timer = 1;
- nohpet = 1;
- return 1;
}
-__setup("apicmaintimer", setup_apicmaintimer);
-
-static __init int setup_noapicmaintimer(char *str)
-{
- apic_runs_main_timer = -1;
- return 1;
-}
-__setup("noapicmaintimer", setup_noapicmaintimer);
-
-static __init int setup_apicpmtimer(char *s)
-{
- apic_calibrate_pmtmr = 1;
- notsc_setup(NULL);
- return setup_apicmaintimer(NULL);
-}
-__setup("apicpmtimer", setup_apicpmtimer);
-
-__setup("noapictimer", setup_noapictimer);
+__setup("noapictimer", setup_noapictimer);

Index: linux-2.6.22-rc4-mm/include/asm-x86_64/apic.h
===================================================================
--- linux-2.6.22-rc4-mm.orig/include/asm-x86_64/apic.h 2007-06-23 14:39:00.000000000 +0200
+++ linux-2.6.22-rc4-mm/include/asm-x86_64/apic.h 2007-06-23 14:39:00.000000000 +0200
@@ -79,8 +79,6 @@ extern void smp_local_timer_interrupt (v
extern void setup_boot_APIC_clock (void);
extern void setup_secondary_APIC_clock (void);
extern int APIC_init_uniprocessor (void);
-extern void disable_APIC_timer(void);
-extern void enable_APIC_timer(void);
extern void setup_apic_routing(void);

extern void setup_APIC_extended_lvt(unsigned char lvt_off, unsigned char vector,
@@ -95,10 +93,6 @@ extern int apic_is_clustered_box(void);
#define K8_APIC_EXT_INT_MSG_EXT 0x7
#define K8_APIC_EXT_LVT_ENTRY_THRESHOLD 0

-void smp_send_timer_broadcast_ipi(void);
-void switch_APIC_timer_to_ipi(void *cpumask);
-void switch_ipi_to_APIC_timer(void *cpumask);
-
#define ARCH_APICTIMER_STOPS_ON_C3 1

extern unsigned boot_cpu_id;

--

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/